github-mcp-tools-usage
Guide for using GitHub MCP tools for repository operations. Use this when working with GitHub repositories, releases, tags, or branches.
Guide for using GitHub MCP tools for repository operations. Use this when working with GitHub repositories, releases, tags, or branches.
Pulls latest changes from remote with conflict resolution. Use when: user wants to pull, fetch changes, or update from remote.
Build a compact, high-signal context brief (files, symbols, recent commits) instead of pasting large code blocks
Use when starting work - guidelines for asking questions and commit policies
Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing false completion claims.
Analyzes current git status and work in progress. Use when: user wants to understand current state, check work status, or see what's changed.
Fetches a GitHub issue, implements the fix, and verifies it. Use when: user wants to fix an issue, implement issue changes, or resolve a bug.
Verify implementation status by scanning local Git repositories for code, tests, and commit history. Use when checking if a feature is actually implemented.
Manages release-please PR merging workflow for monorepos. Handles batch merging, conflict resolution through PR closure/recreation, and iterative processing until all PRs are merged. Use when merging release PRs, handling PR conflicts, or managing release automation in monorepos.
Use throughout all work - ensures GitHub issues are updated continuously as work happens, not batched at the end
Comprehensive guide for working with GitHub data and APIs. Use when fetching issues, PRs, discussions, comments, reviews, or any GitHub content. Covers tool selection (mcp_github vs fetch vs semantic search), complete conversation fetching patterns, pagination handling, and common workflows. Critical for avoiding standard API failures when fetching comments/reviews—MCP tools required.
Create or update GitHub issue for the story and sub-issues for tasks
Generate semantic commit messages following conventional commit format for agentconfig.org. Use when creating commits, reviewing staged changes, or when the user asks for help with commit messages.
Manage and rebase chains of dependent Git branches (stacked branches). Use when working with multiple dependent PRs, feature branches that build on each other, or maintaining clean branch hierarchies. Automates the tedious process of rebasing or merging entire branch chains.
Creates a GitHub issue with structured content using gh CLI. Use when: user wants to create an issue, report a bug, or propose a feature.
Sets up autonomous TDD loops at project level. Use when installing Ralph loops in projects, updating hooks based on latest practices, or troubleshooting loop behavior. Based on Ryan Carson's Ralph Wiggum technique.
Manage git worktrees for parallel branch work. PROACTIVELY USE when user mentions working on a PR, new feature, or new task - ask if they want to create a worktree BEFORE starting implementation.
Commits changes and pushes to remote repository. Use when: user wants to commit and push in one flow.
Extract, consolidate, and prioritize all comments from GitHub Pull Requests for systematic code review. Fetches both inline review comments and general PR conversation, then analyzes and organizes them by priority (critical bugs/security, design improvements, style nitpicks). Use when working with PR reviews, consolidating feedback from multiple reviewers, or creating action plans from review comments.
Load cross-project context in monorepos. Lists available workspace projects or loads specific project context (CLAUDE.md, package.json, README, STATUS.json). Supports pnpm, npm/yarn, Lerna workspaces. Use when working in monorepo and need context from sibling projects.
WHEN: User requests Go code work (implement, fix, add, refactor) or mentions @ldd in a Go project. Orchestrates complete workflow (Phases 1-5): design → test → implement → lint → fix → documentation. Auto-triggers parallel quality analysis and iterative fix loop until code is commit-ready.